Dataset Information

Extracellular vesicle miRNA predict FDG-PET status in patients with classical Hodgkin Lymphoma.

ABSTRACT: Minimally-invasive tools to assess tumour presence and burden may improve clinical management. FDG-PET (metabolic) imaging is the current gold standard for interim response assessment in patients with classical Hodgkin Lymphoma (cHL), but this technique cannot be repeated frequently. Here we show that microRNAs (miRNA) associated with tumour-secreted extracellular vesicles (EVs) in the circulation of cHL patients may improve response assessment. Small RNA sequencing and qRT-PCR reveal that the relative abundance of cHL-expressed miRNAs, miR-127-3p, miR-155-5p, miR-21-5p, miR-24-3p and let-7a-5p is up to hundred-fold increased in plasma EVs of cHL patients pre-treatment when compared to complete metabolic responders (CMR). Notably, in partial responders (PR) or treatment-refractory cases (n = 10) the EV-miRNA levels remain elevated. In comparison, tumour specific copy number variations (CNV) were detected in cell-free DNA of 8 out of 10 newly diagnosed cHL patients but not in patients with PR. Combining EV-miR-127-3p and/or EV-let-7a-5p levels, with serum TARC (a validated protein cHL biomarker), increases the accuracy for predicting PET-status (n = 129) to an area under the curve of 0.93 (CI: 0.87-0.99), 93.5% sensitivity, 83.8/85.0% specificity and a negative predictive value of 96%. Thus the level of tumour-associated miRNAs in plasma EVs is predictive of metabolic tumour activity in cHL patients. Our findings suggest that plasma EV-miRNA are useful for detection of small residual lesions and may be applied as serial response prediction tool.

SUBMITTER: Drees EEE

PROVIDER: S-EPMC8282992 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:ObjectivesRelapse occurs in ~20% of patients with classical Hodgkin lymphoma (cHL) despite treatment adaption based on 2-deoxy-2-[18F]fluoro-D-glucose positron emission tomography/computed tomography response. The objective was to evaluate pre-treatment FDG PET/CT-derived machine learning (ML) models for predicting outcome in patients with cHL.MethodsAll cHL patients undergoing pre-treatment PET/CT at our institution between 2008 and 2018 were retrospectively identified. A 1.5 × mean liver standardised uptake value (SUV) and a fixed 4.0 SUV threshold were used to segment PET/CT data. Feature extraction was performed using PyRadiomics with ComBat harmonisation. Training (80%) and test (20%) cohorts stratified around 2-year event-free survival (EFS), age, sex, ethnicity and disease stage were defined. Seven ML models were trained and hyperparameters tuned using stratified 5-fold cross-validation. Area under the curve (AUC) from receiver operator characteristic analysis was used to assess performance.ResultsA total of 289 patients (153 males), median age 36 (range 16-88 years), were included. There was no significant difference between training (n = 231) and test cohorts (n = 58) (p value > 0.05). A ridge regression model using a 1.5 × mean liver SUV segmentation had the highest performance, with mean training, validation and test AUCs of 0.82 ± 0.002, 0.79 ± 0.01 and 0.81 ± 0.12. However, there was no significant difference between a logistic model derived from metabolic tumour volume and clinical features or the highest performing radiomic model.ConclusionsOutcome prediction using pre-treatment FDG PET/CT-derived ML models is feasible in cHL patients. Further work is needed to determine optimum predictive thresholds for clinical use.Key points• A fixed threshold segmentation method led to more robust radiomic features. • A radiomic-based model for predicting 2-year event-free survival in classical Hodgkin lymphoma patients is feasible. • A predictive model based on ridge regression was the best performing model on our dataset.

Project description:PurposeFor pediatric lymphoma, quantitative FDG PET/CT imaging features such as metabolic tumor volume (MTV) are important for prognosis and risk stratification strategies. However, feature extraction is difficult and time-consuming in cases of high disease burden. The purpose of this study was to fully automate the measurement of PET imaging features in PET/CT images of pediatric lymphoma.Methods18F-FDG PET/CT baseline images of 100 pediatric Hodgkin lymphoma patients were retrospectively analyzed. Two nuclear medicine physicians identified and segmented FDG avid disease using PET thresholding methods. Both PET and CT images were used as inputs to a three-dimensional patch-based, multi-resolution pathway convolutional neural network architecture, DeepMedic. The model was trained to replicate physician segmentations using an ensemble of three networks trained with 5-fold cross-validation. The maximum SUV (SUVmax), MTV, total lesion glycolysis (TLG), surface-area-to-volume ratio (SA/MTV), and a measure of disease spread (Dmaxpatient) were extracted from the model output. Pearson's correlation coefficient and relative percent differences were calculated between automated and physician-extracted features.ResultsMedian Dice similarity coefficient of patient contours between automated and physician contours was 0.86 (IQR 0.78-0.91). Automated SUVmax values matched exactly the physician determined values in 81/100 cases, with Pearson's correlation coefficient (R) of 0.95. Automated MTV was strongly correlated with physician MTV (R = 0.88), though it was slightly underestimated with a median (IQR) relative difference of - 4.3% (- 10.0-5.7%). Agreement of TLG was excellent (R = 0.94), with median (IQR) relative difference of - 0.4% (- 5.2-7.0%). Median relative percent differences were 6.8% (R = 0.91; IQR 1.6-4.3%) for SA/MTV, and 4.5% (R = 0.51; IQR - 7.5-40.9%) for Dmaxpatient, which was the most difficult feature to quantify automatically.ConclusionsAn automated method using an ensemble of multi-resolution pathway 3D CNNs was able to quantify PET imaging features of lymphoma on baseline FDG PET/CT images with excellent agreement to reference physician PET segmentation. Automated methods with faster throughput for PET quantitation, such as MTV and TLG, show promise in more accessible clinical and research applications.

Project description:Classical Hodgkin lymphomas (cHLs) include small numbers of malignant Reed-Sternberg cells within an extensive but ineffective inflammatory/immune cell infiltrate. In cHL, chromosome 9p24.1/PD-L1/PD-L2 alterations increase the abundance of the PD-1 ligands, PD-L1 and PD-L2, and their further induction through Janus kinase 2-signal transducers and activators of transcription signaling. The unique composition of cHL limits its analysis with high-throughput genomic assays. Therefore, the precise incidence, nature, and prognostic significance of PD-L1/PD-L2 alterations in cHL remain undefined.We used a fluorescent in situ hybridization assay to evaluate CD274/PD-L1 and PDCD1LG2/PD-L2 alterations in 108 biopsy specimens from patients with newly diagnosed cHL who were treated with the Stanford V regimen and had long-term follow-up. In each case, the frequency and magnitude of 9p24.1 alterations-polysomy, copy gain, and amplification-were determined, and the expression of PD-L1 and PD-L2 was evaluated by immunohistochemistry. We also assessed the association of 9p24.1 alterations with clinical parameters, which included stage (early stage I/II favorable risk, early stage unfavorable risk, advanced stage [AS] III/IV) and progression-free survival (PFS).Ninety-seven percent of all evaluated cHLs had concordant alterations of the PD-L1 and PD-L2 loci (polysomy, 5% [five of 108]; copy gain, 56% [61 of 108]; amplification, 36% [39 of 108]). There was an association between PD-L1 protein expression and relative genetic alterations in this series. PFS was significantly shorter for patients with 9p24.1 amplification, and the incidence of 9p24.1 amplification was increased in patients with AS cHL.PD-L1/PD-L2 alterations are a defining feature of cHL. Amplification of 9p24.1 is more common in patients with AS disease and associated with shorter PFS in this series. Further analyses of 9p24.1 alterations in patients treated with standard cHL induction regimens or checkpoint blockade are warranted.

Dataset Information

Extracellular vesicle miRNA predict FDG-PET status in patients with classical Hodgkin Lymphoma.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets